migrate

Pass

Audited by Gen Agent Trust Hub on Aug 30, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes shell commands using 'npx playwright test' to validate converted test files and performs file system operations to remove legacy test suites and configurations.
  • [INDIRECT_PROMPT_INJECTION]: The skill possesses an attack surface for indirect prompt injection by ingesting and processing untrusted test files. Ingestion points: Local Cypress and Selenium test files, including scripts and package manifests. Boundary markers: Absent; instructions do not specify the use of delimiters when reading file content. Capability inventory: The skill can execute shell commands and delete files based on the processed information. Sanitization: No sanitization or validation of the input test file content is performed before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 30, 2026, 03:47 AM
Security Audit — agent-trust-hub — migrate